对比7种强度归一化方法在膝关节MRI分割中的表现，发现其对跨域泛化影响有限。
A Systematic Benchmark of Intensity Normalisation Methods for 3D Knee MRI Segmentation and Cross-Domain Generalisability
- 系统比较7种归一化方法对3D U-Net模型的影响
- 外部数据集上性能下降显著，最优方法仅小幅提升
- 提示需结合其他策略应对扫描仪差异带来的域偏移
深度学习模型在医学影像临床部署中需要具备鲁棒的开箱即用性能。影响模型泛化能力的重要但研究不足的因素是图像强度归一化，尤其在磁共振成像（MRI）中，不同扫描仪和协议导致图像强度差异显著。本研究系统对比了七种归一化方法及其对3D U-Net模型在膝关节MRI中半月板分割性能的影响，包括标准缩放、直方图匹配与基于高斯混合模型（GMM）的方法。模型在IWOAI 2019数据集上训练，并在内部和外部测试集（SKM-TEA）上评估泛化能力。内部性能相近，但在外部数据上差异明显，其中Z-score、Nyúl直方图匹配和CLAHE表现更稳健。然而，这些方法间的差异远小于数据集间性能下降幅度。总体而言，虽然强度归一化对泛化有可测量影响，但其作用远小于域偏移的影响，凸显了在实际部署中需采用互补策略的重要性。
原文摘要 · Abstract (English)
Robust out-of-the-box performance is essential for the clinical deployment of deep learning models in medical imaging. An important but underexplored factor affecting model generalisability is intensity normalisation, particularly for magnetic resonance imaging (MRI), where image intensities vary across scanners and protocols. In this study, we systematically compared seven normalisation methods and their impact on the performance of a 3D U-Net model for meniscus segmentation from knee MRI. The methods included standard scaling approaches, histogram-based techniques, and a Gaussian Mixture Model (GMM)-based method. Models were trained on the IWOAI 2019 dataset and evaluated on both internal and external test sets (SKM-TEA) to assess generalisability. Performance was similar internally but differences were significant on external data, with Z-score, Nyúl histogram matching, and CLAHE showing greater robustness than other methods. However, these differences were small compared to the significant performance drop observed between datasets. Overall, while intensity normalisation had a measurable effect on model generalisability, its impact was limited relative to the effects of domain shift, highlighting the need for complementary strategies for robust deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。